[v1,2/2] thermal/debugfs: Add thermal debugfs information for mitigation episodes

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 33332d401b13..a0cbe8d7b945 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -367,6 +367,7 @@  static void handle_thermal_trip(struct thermal_zone_device *tz,
 			thermal_notify_tz_trip_up(tz->id,
 						  thermal_zone_trip_id(tz, trip),
 						  tz->temperature);
+			thermal_debug_tz_trip_up(tz, trip);
 			trip->threshold = trip->temperature - trip->hysteresis;
 		} else {
 			trip->threshold = trip->temperature;
@@ -386,6 +387,7 @@  static void handle_thermal_trip(struct thermal_zone_device *tz,
 			thermal_notify_tz_trip_down(tz->id,
 						    thermal_zone_trip_id(tz, trip),
 						    tz->temperature);
+			thermal_debug_tz_trip_down(tz, trip);
 			trip->threshold = trip->temperature;
 		} else {
 			trip->threshold = trip->temperature - trip->hysteresis;
@@ -417,6 +419,7 @@  static void update_temperature(struct thermal_zone_device *tz)
 	trace_thermal_temperature(tz);
 
 	thermal_genl_sampling_temp(tz->id, temp);
+	thermal_debug_update_temp(tz);
 }
 
 static void thermal_zone_device_init(struct thermal_zone_device *tz)
@@ -1396,6 +1399,8 @@  thermal_zone_device_register_with_trips(const char *type, struct thermal_trip *t
 
 	thermal_notify_tz_create(tz->id, tz->type);
 
+	thermal_debug_tz_add(tz);
+
 	return tz;
 
 unregister:
@@ -1461,6 +1466,8 @@  void thermal_zone_device_unregister(struct thermal_zone_device *tz)
 	if (!tz)
 		return;
 
+	thermal_debug_tz_remove(tz);
+
 	tz_id = tz->id;
 
 	mutex_lock(&thermal_list_lock);
diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
index 295f7a2a7d0d..372664d0e1ae 100644
--- a/drivers/thermal/thermal_debugfs.c
+++ b/drivers/thermal/thermal_debugfs.c
@@ -13,8 +13,11 @@ 
 #include <linux/mutex.h>
 #include <linux/thermal.h>
 
+#include "thermal_core.h"
+
 static struct dentry *d_root;
 static struct dentry *d_cdev;
+static struct dentry *d_tz;
 
 /*
  * Length of the string containing the thermal zone id, including the
@@ -53,6 +56,44 @@  struct cdev_debugfs {
 	struct list_head duration_list[CDEVSTATS_HASH_SIZE];
 };
 
+/*
+ * The trip_stats structure has the relevant information to show the
+ * statistics related to a trip point violation during a mitigation
+ * episode.
+ */
+struct trip_stats {
+	ktime_t timestamp;
+	ktime_t duration;
+	int count;
+	int max;
+	int min;
+	int avg;
+};
+
+/*
+ * The tz_events structure describes a mitigation episode. A
+ * mitigation episode is when the mitigation begins and ends. During
+ * this episode we can have multiple trip points crossed the way up
+ * and down if there are multiple trip describes in the firmware.
+ */
+struct tz_events {
+	struct list_head list;
+	struct trip_stats *trip_stats;
+	ktime_t timestamp;
+	ktime_t duration;
+};
+
+/*
+ * The tz_debugfs structure contains the list of the mitigation
+ * episodes and has to track which trip point has been crossed in
+ * order to handle correctly nested trip point mitigation episodes.
+ */
+struct tz_debugfs {
+	struct list_head tz_events;
+	int *trips_crossed;
+	int trip_index;
+};
+
 /*
  * The thermal_debugfs structure is the common structure used by the
  * cooling device to compute the statistics and the thermal to measure
@@ -63,6 +104,7 @@  struct thermal_debugfs {
 	struct mutex lock;
 	union {
 		struct cdev_debugfs cdev;
+		struct tz_debugfs tz;
 	};
 };
 
@@ -73,6 +115,10 @@  void thermal_debug_init(void)
 		return;
 
 	d_cdev = debugfs_create_dir("cooling_devices", d_root);
+	if (!d_cdev)
+		return;
+
+	d_tz = debugfs_create_dir("thermal_zones", d_root);
 }
 
 static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
@@ -348,7 +394,289 @@  void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev)
 	if (!dfs)
 		return;
 
+	debugfs_remove(dfs->d_top);
 	thermal_debugfs_cdev_reset(&dfs->cdev);
 	cdev->debugfs = NULL;
-	thermal_debugfs_remove_id(dfs);
+	kfree(dfs);
+}
+
+static struct tz_events *thermal_debugfs_tz_event_alloc(struct thermal_zone_device *tz,
+							ktime_t now)
+{
+	struct tz_events *tze;
+	struct trip_stats *trip_stats;
+	int i;
+
+	tze = kzalloc(sizeof(*tze), GFP_KERNEL);
+	if (!tze)
+		return NULL;
+
+	INIT_LIST_HEAD(&tze->list);
+	tze->timestamp = now;
+
+	trip_stats = kzalloc(sizeof(struct trip_stats) * tz->num_trips, GFP_KERNEL);
+	if (!trip_stats) {
+		kfree(tze);
+		return NULL;
+	}
+
+	for (i = 0; i < tz->num_trips; i++) {
+		trip_stats[i].min = INT_MAX;
+		trip_stats[i].max = INT_MIN;
+	}
+	
+	tze->trip_stats = trip_stats;
+
+	return tze;
+}
+
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, struct thermal_trip *trip)
+{
+	struct tz_events *tze;
+	struct thermal_debugfs *dfs = tz->debugfs;
+	int temperature = tz->temperature;
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	ktime_t now = ktime_get();
+
+	if (!dfs)
+		return;
+
+	mutex_lock(&dfs->lock);
+
+	/*
+	 * The mitigation is starting. A mitigation can contain
+	 * several episodes where each of them is related to a
+	 * temperature crossing a trip point. The episodes are
+	 * nested. That means when the temperature is crossing the
+	 * first trip point, the duration begins to be measured. If
+	 * the temperature continues to increase and reaches the
+	 * second trip point, the duration of the first trip must be
+	 * also accumulated.
+	 *
+	 * eg.
+	 *
+	 * temp
+	 *   ^
+	 *   |             --------
+	 * trip 2         /        \         ------
+	 *   |           /|        |\      /|      |\
+	 * trip 1       / |        | `----  |      | \
+	 *   |         /| |        |        |      | |\
+	 * trip 0     / | |        |        |      | | \
+	 *   |       /| | |        |        |      | | |\
+	 *   |      / | | |        |        |      | | | `--
+	 *   |     /  | | |        |        |      | | |     
+	 *   |-----   | | |        |        |      | | |      
+	 *   |        | | |        |        |      | | |
+	 *    --------|-|-|--------|--------|------|-|-|------------------> time
+	 *            | | |<--t2-->|        |<-t2'>| | |
+	 *            | |                            | |
+	 *            | |<------------t1------------>| |
+	 *            |                                |
+	 *            |<-------------t0--------------->|
+	 *
+	 */
+	if (dfs->tz.trip_index < 0) {
+		tze = thermal_debugfs_tz_event_alloc(tz, now);
+		if (!tze)
+			return;
+
+		list_add(&tze->list, &dfs->tz.tz_events);
+	}
+
+	dfs->tz.trip_index++;
+	dfs->tz.trips_crossed[dfs->tz.trip_index] = trip_id;
+
+	tze = list_first_entry(&dfs->tz.tz_events, struct tz_events, list);
+	tze->trip_stats[trip_id].timestamp = now;
+        tze->trip_stats[trip_id].max = max(tze->trip_stats[trip_id].max, temperature);
+	tze->trip_stats[trip_id].min = min(tze->trip_stats[trip_id].min, temperature);
+	tze->trip_stats[trip_id].avg = tze->trip_stats[trip_id].avg +
+		(temperature - tze->trip_stats[trip_id].avg) / tze->trip_stats[trip_id].count;
+
+	mutex_unlock(&dfs->lock);
+}
+
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz, struct thermal_trip *trip)
+{
+	struct thermal_debugfs *dfs = tz->debugfs;
+	struct tz_events *tze;
+	int trip_id = thermal_zone_trip_id(tz, trip);
+	ktime_t delta, now = ktime_get();
+
+	if (!dfs)
+		return;
+
+	/*
+	 * The temperature crosses the way down but there was not
+	 * mitigation detected before. That may happen when the
+	 * temperature is greater than a trip point when registering a
+	 * thermal zone, which is a common use case as the kernel has
+	 * no mitigation mechanism yet at boot time.
+	 */
+	if (dfs->tz.trip_index < 0)
+		return;
+	
+	mutex_lock(&dfs->lock);
+	
+	tze = list_first_entry(&dfs->tz.tz_events, struct tz_events, list);
+
+	delta = ktime_sub(now, tze->trip_stats[trip_id].timestamp);
+	tze->trip_stats[trip_id].duration = ktime_add(delta, tze->trip_stats[trip_id].duration);
+
+	dfs->tz.trip_index--;
+
+	/*
+	 * This event closes the mitigation as we are crossing the
+	 * last trip point the way down.
+	 */
+	if (dfs->tz.trip_index < 0)
+		tze->duration = ktime_sub(now, tze->timestamp);
+
+	mutex_unlock(&dfs->lock);
+}
+
+void thermal_debug_update_temp(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *dfs = tz->debugfs;
+	struct tz_events *tze;
+	int trip;
+
+	if (!dfs)
+		return;
+
+	mutex_lock(&dfs->lock);
+
+	if (dfs->tz.trip_index >= 0) {
+		trip = dfs->tz.trip_index;
+		tze = list_first_entry(&dfs->tz.tz_events, struct tz_events, list);
+		tze->trip_stats[trip].count++;
+		tze->trip_stats[trip].max = max(tze->trip_stats[trip].max, tz->temperature);
+		tze->trip_stats[trip].min = min(tze->trip_stats[trip].min, tz->temperature);
+		tze->trip_stats[trip].avg = tze->trip_stats[trip].avg +
+			(tz->temperature - tze->trip_stats[trip].avg) / tze->trip_stats[trip].count;
+	}
+
+	mutex_unlock(&dfs->lock);
+}
+
+static void *tze_seq_start(struct seq_file *s, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *dfs = tz->debugfs;
+	struct tz_debugfs *tzd = &dfs->tz;
+
+	mutex_lock(&dfs->lock);
+
+	return seq_list_start(&tzd->tz_events, *pos);
+}
+
+static void *tze_seq_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *dfs = tz->debugfs;
+        struct tz_debugfs *tzd = &dfs->tz;
+
+	return seq_list_next(v, &tzd->tz_events, pos);
+}
+
+static void tze_seq_stop(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct thermal_debugfs *dfs = tz->debugfs;
+
+	mutex_unlock(&dfs->lock);
+}
+
+static int tze_seq_show(struct seq_file *s, void *v)
+{
+	struct thermal_zone_device *tz = s->private;
+	struct tz_events *tze;
+	int i;
+
+	tze = list_entry((struct list_head *)v, struct tz_events, list);
+
+	seq_printf(s, ",-Mitigation at %lluus, duration=%llums\n", ktime_to_us(tze->timestamp),
+		   ktime_to_ms(tze->duration));
+
+	seq_printf(s, "| trip |     type | temp(°mC) | hyst(°mC) |  duration  |  avg(°mC) |  min(°mC) |  max(°mC) |\n");
+	
+	for (i = 0; i < tz->num_trips; i++) {
+
+		struct thermal_trip trip;
+		const char *type;
+		
+		if (__thermal_zone_get_trip(tz, i, &trip))
+			continue;
+
+		/*
+		 * There is no possible mitigation happening at the
+		 * critical trip point, so the stats will be always
+		 * zero, skip this trip point
+		 */
+		if (trip.type == THERMAL_TRIP_CRITICAL)
+			continue;
+
+		if (trip.type == THERMAL_TRIP_PASSIVE)
+			type = "passive";
+		else if (trip.type == THERMAL_TRIP_ACTIVE)
+			type = "active";
+		else
+			type = "hot";
+
+		seq_printf(s, "| %*d | %*s | %*d | %*d | %*lld | %*d | %*d | %*d |\n",
+			   4 , i,
+			   8, type,
+			   9, trip.temperature,
+			   9, trip.hysteresis,
+			   10, ktime_to_ms(tze->trip_stats[i].duration),
+			   9, tze->trip_stats[i].avg,
+			   9, tze->trip_stats[i].min,
+			   9, tze->trip_stats[i].max);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations tze_sops = {
+	.start = tze_seq_start,
+	.next = tze_seq_next,
+	.stop = tze_seq_stop,
+	.show = tze_seq_show,
+};
+
+DEFINE_SEQ_ATTRIBUTE(tze);
+
+void thermal_debug_tz_add(struct thermal_zone_device *tz)
+{
+	struct thermal_debugfs *dfs;
+	struct tz_debugfs *tzd;
+
+	dfs = thermal_debugfs_add_id(d_tz, tz->id);
+	if (!dfs)
+		return;
+
+	tzd = &dfs->tz;
+
+	tzd->trips_crossed = kzalloc(sizeof(int) * tz->num_trips, GFP_KERNEL);
+	if (!tzd->trips_crossed) {
+		thermal_debugfs_remove_id(dfs);
+		return;
+	}
+
+	/*
+	 * Trip index '-1' means no mitigation
+	 */
+	tzd->trip_index = -1;
+	INIT_LIST_HEAD(&tzd->tz_events);
+
+	debugfs_create_file("mitigations", 0400, dfs->d_top, tz, &tze_fops);
+	
+	tz->debugfs = dfs;
+}
+
+void thermal_debug_tz_remove(struct thermal_zone_device *tz)
+{
+	thermal_debugfs_remove_id(tz->debugfs);
+	tz->debugfs = NULL;
 }
diff --git a/drivers/thermal/thermal_debugfs.h b/drivers/thermal/thermal_debugfs.h
index 674eec369328..b8b45bf509dd 100644
--- a/drivers/thermal/thermal_debugfs.h
+++ b/drivers/thermal/thermal_debugfs.h
@@ -5,9 +5,19 @@  void thermal_debug_init(void);
 void thermal_debug_cdev_add(struct thermal_cooling_device *cdev);
 void thermal_debug_cdev_remove(struct thermal_cooling_device *cdev);
 void thermal_debug_cdev_transition(struct thermal_cooling_device *cdev, int state);
+void thermal_debug_tz_add(struct thermal_zone_device *tz);
+void thermal_debug_tz_remove(struct thermal_zone_device *tz);
+void thermal_debug_tz_trip_up(struct thermal_zone_device *tz, struct thermal_trip *trip);
+void thermal_debug_tz_trip_down(struct thermal_zone_device *tz, struct thermal_trip *trip);
+void thermal_debug_update_temp(struct thermal_zone_device *tz);
 #else
 static inline void thermal_debug_init(void) {}
 static inline void thermal_debug_cdev_add(struct thermal_cooling_device *) {}
 static inline void thermal_debug_cdev_remove(struct thermal_cooling_device *) {}
 static inline void thermal_debug_cdev_transition(struct thermal_cooling_device *, int) {}
+static inline void thermal_debug_tz_add(struct thermal_zone_device *) {}
+static inline void thermal_debug_tz_remove(struct thermal_zone_device *) {}
+static inline void thermal_debug_tz_trip_up(struct thermal_zone_device *, struct thermal_trip *trip) {};
+static inline void thermal_debug_tz_trip_down(struct thermal_zone_device *, struct thermal_trip *trip) {}
+static inline void thermal_debug_update_temp(struct thermal_zone_device *) {}
 #endif /* CONFIG_THERMAL_DEBUGFS */